JP2005284471A - Image processing apparatus and method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To prevent wasteful image processing by eliminating unnecessary brightness information in an image for preceding vehicle recognition and an image for white line recognition in generation of these images. <P>SOLUTION: Among brightness information in an image in front of an own-vehicle, information, from which information about a value not more than a minimum lightness value (Ga_B min) and not less than a maximum lightness value (Ga_B max) of an image of a matter is discarded, is generated as the image for the preceding vehicle recognition. And among the brightness information in the image in front of the own-vehicle, information, from which information about a value not more than a minimum lightness value (Gb_B min) and not less than a maximum lightness value (Gb_B max) of an image of a road surface is discarded, is generated as the image for the white line recognition. The image for the preceding vehicle recognition and the image for the white line recognition not including information unnecessary for a preceding vehicle tracing system is provided thereto and the system is improved in readiness (real-time property). <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to an image processing apparatus and an image processing method. Specifically, in a vehicle such as an automobile, for example, an image processing apparatus and an image processing method used in a vehicle travel support system such as tracking a preceding vehicle, and in particular, process an image of an imaging device having a high limitable contrast ratio. The present invention relates to an image processing apparatus and an image processing method.

  Here, the “limit light / dark ratio” refers to the ratio between the minimum value and the maximum value of the brightness (brightness or luminance) of a subject that can be photographed by the imaging device. Usually expressed in decibel values (dynamic range). The higher the limit light / dark ratio, the more accurately the bright and dark parts of the image can be reproduced.

  In general, in a preceding vehicle tracking system, various positions such as the position and travel speed of a vehicle in front of the own vehicle (hereinafter referred to as “preceding vehicle”), the speed difference from the own vehicle, and the distance from the preceding vehicle (inter-vehicle distance) are various. Information is required, but when obtaining such information, it is necessary to immediately respond to sudden movements of the preceding vehicle (sudden stop, etc.) and take emergency measures such as necessary avoidance measures and braking measures promptly. In particular, a high level of responsiveness (real time) is required.

  In this regard, Patent Document 1 discloses a technique in which a laser radar and an imaging device are used in combination. The gist of this technology is to use the preceding vehicle information detected by the laser radar to cut out a specific area of the image information (“processing area” in the same document), and to set only the cut-out area as the object of image processing. This eliminates useless image processing and achieves high-speed image processing.

  This prior art imaging device is premised on the use of a CCD (charge transfer device) camera as specified in the document, but the dynamic range of a CCD camera is generally described in Non-Patent Document 1. As it is, it is only about 30-40 dB at most. This dynamic range is far below the required dynamic range (100 dB or more) when shooting images with a wide variety of brightness from a bright subject illuminated by sunlight to a dark subject at night. When applied to on-vehicle equipment such as a tracking system, some measure for improving the dynamic range is indispensable.

  As such measures, for example, as described in Non-Patent Document 2, a technique for expanding a dynamic range by combining images of a plurality of scenes with different exposure conditions, or as described in Non-Patent Document 3 is described. In addition, a technique for compressing a dynamic range by suppressing a low spatial frequency component of an image by hardware processing is known. However, in any case, the overhead of image processing is large, which is not preferable in terms of real-time characteristics, and is not preferable in terms of cost if it requires hardware processing.

  Therefore, the applicant of the present application previously described an “image data conversion apparatus and camera apparatus” (Japanese Patent Application No. 2004-2004) using a CMOS (complementary metal oxide semiconductor) camera, which is an imaging device with a high dynamic range, instead of a CCD camera. 42187 / February 19, 2004). This proposed technology is "Converting image data with a wide dynamic range into image data with a narrow dynamic range", so as not to incur the disadvantages (overhead problems and cost problems) of the above-mentioned conventional technology. Is.

  The first advantage of a CMOS camera when compared with a CCD camera is that the dynamic range is wide as described above (a CMOS camera of 130 dB is also in practical use according to Non-Patent Document 1), and the second is It is possible to perform random access of the image sensor (thus, extraction of pixel information of an arbitrary region as well as all pixels). If this CMOS camera is used, the required dynamic range (over 100 dB) for outdoor photography can be ensured without incurring the disadvantages of the above-described prior art (overhead problems and cost problems). By taking out an image of a specific area and subjecting only the image of the specific area to image processing, useless image processing can be eliminated, and high-speed image processing (advanced real-time performance) can be achieved.

  However, wasteful image processing cannot be completely eliminated simply by using only an image of a specific area of a CMOS camera, for example, an image of a specific area including a preceding vehicle. As described above, since the dynamic range of the CMOS camera is quite wide, the image of the specific area includes a lot of “unnecessary brightness information”.

  That is, the image of the specific area including the preceding vehicle includes not only information necessary for the recognition of the preceding vehicle but also high luminance information such as sunlight and low luminance information such as shade, and the CMOS camera. Because of the high dynamic range, the ratio of these unnecessary brightness information (high brightness information such as sunlight and low brightness information such as shade) that occupies the image is considerably large, so that unnecessary brightness information is wasted. I can't deny image processing.

  In addition, the preceding vehicle tracking system requires not only an image of the preceding vehicle but also a white line image on the road surface. For example, assume that when the vehicle is traveling on a road composed of a plurality of lanes, a vehicle traveling in the same lane and a vehicle traveling in an adjacent lane exist in front of the vehicle. In this case, the vehicle that should be recognized as the preceding vehicle is the former (the vehicle that is traveling in the same lane), and the latter (the vehicle that is traveling in the adjacent lane) must not be recognized as the preceding vehicle. Since the information necessary for the determination of the preceding vehicle is generally information on the lane boundary line (white line) on the road surface, in addition to the image of the preceding vehicle, in addition to the image of the preceding vehicle, An image of the white line on the road surface is also required.

Japanese Patent No. 3264060 “Video Information Industrial”, Industrial Development Organization Co., Ltd., January 2003 issue, P20-P51 Yamada, 2 others, “Wide Dynamic Range Vision Sensor”, Toyota Central R & D Review, June 1995, Vol. 30, No. 2, [Search January 3, 2004], Internet <URL: http : //www.tytlabs.co.jp/office/library/review/rev302pdf/302_035yamada.pdf Soga, 3 others, “Image processing technology for rear camera (2) Visibility improvement by dynamic range compression”, Toyota Central R & D Review, June 2003, Vol. 38, No. 2, [2004 1 Search on March 3], Internet <URL: http://www.tytlabs.co.jp/office/library/review/rev382pdf/382_037soga.pdf

  As described above, the prior art has a problem to be improved in terms of the responsiveness (real-time property) of the preceding vehicle tracking system. The image of the CMOS camera has a large amount of information corresponding to its dynamic range, and the preceding vehicle tracking system processes two images (the preceding vehicle recognition image and the white line recognition image) of the preceding vehicle image and the white line image. Because it must be.

  Therefore, the present invention eliminates unnecessary brightness information of the preceding vehicle recognition image and the white line recognition image so as not to perform useless image processing. An object of the present invention is to provide an image processing apparatus and an image processing method intended to improve the responsiveness (real-time property) of the system.

The image processing apparatus according to the present invention is based on detection information from a radar that detects an object in front of the host vehicle and a road surface immediately in front of the host vehicle. In the image processing apparatus that extracts the preceding vehicle recognition image and the white line recognition image on the road surface, the object is detected from the image ahead of the host vehicle according to the detection information of the object ahead of the host vehicle detected by the radar. The first brightness value detecting means for detecting the lowest brightness value and the highest brightness value of the object image, and the detection information of the road surface immediately in front of the own vehicle detected by the radar. A second lightness value detecting means for extracting a road surface image including the road surface from an image ahead of the vehicle and detecting a minimum lightness value and a maximum lightness value of the road surface image; and brightness information of the image ahead of the vehicle. Image generation means for preceding vehicle recognition for generating, as the preceding vehicle recognition image, information obtained by discarding information below the minimum brightness value and above the maximum brightness value of the object image, and brightness information of the image ahead of the host vehicle And white line recognition image generating means for generating, as the white line recognition image, information obtained by discarding information below the minimum brightness value and above the maximum brightness value of the road surface image.
In the present invention, the brightness information of the image ahead of the vehicle is generated as the preceding vehicle recognition image, which is obtained by truncating the information below the minimum brightness value and above the maximum brightness value of the object image. Of the brightness information of the image, information obtained by discarding information below the minimum brightness value and above the maximum brightness value of the road surface image is generated as the white line recognition image.

According to the present invention, information unnecessary for the preceding vehicle tracking system, that is, an image for recognizing a preceding vehicle that does not include information below the minimum brightness value of the object image and above the maximum brightness value, and below the minimum brightness value of the road surface image and the maximum Since white line recognition images that do not contain information above the brightness value are generated, these images are given to the preceding vehicle tracking system, eliminating unnecessary image processing of the system, improving the operation speed, and responsiveness ( Real-time property) can be improved.
Here, it is preferable to use a CMOS camera for the imaging device. Since the CMOS camera can take out an image of an arbitrary area, that is, can be randomly accessed and can take out an image of a minimum size that does not include unnecessary pixel information, This is because the burden of image processing can be further reduced.

  Embodiments of the present invention will be described below with reference to the drawings. It should be noted that the specific details or examples in the following description and the illustrations of numerical values, character strings, and other symbols are only for reference in order to clarify the idea of the present invention, and the present invention may be used in whole or in part. Obviously, the idea of the invention is not limited. In addition, a well-known technique, a well-known procedure, a well-known architecture, a well-known circuit configuration, and the like (hereinafter, “well-known matter”) are not described in detail, but this is also to simplify the description. Not all or part of the matter is intentionally excluded. Such well-known matters are known to those skilled in the art at the time of filing of the present invention, and are naturally included in the following description.

  FIG. 1A is a system configuration diagram of the embodiment. A vehicle 1 (hereinafter referred to as “own vehicle 1”) includes a laser radar 2 (radar), a CMOS camera 3 (imaging device), and an image processing unit 4 (first brightness value detection means, second brightness value detection). Means, a preceding vehicle recognition image generation means, and a white line recognition image generation means). The preceding vehicle tracking system is, for example, based on preceding vehicle information (information such as distance, position and speed to the preceding vehicle) as described in Japanese Patent Application Laid-Open No. 8-285941. This is a system that controls to follow the preceding vehicle while adjusting the engine output (braking force in some cases) and the steering amount.

  The laser radar 2 uniformly scans a variable or fixed monitoring area set in front of the host vehicle 1 with a pencil beam shaped laser beam 2a (horizontal scanning and vertical scanning), and a laser beam from an object in the monitoring area. The object position (azimuth and elevation angle) is determined from the beam scanning angle (horizontal angle and vertical angle) when the reflected wave 2a is received, and the distance to the object is determined from the time difference between the beam emission and the reflected wave reception. is there. Note that a radio wave instead of the laser, for example, a millimeter wave radar may be used. In short, any distance measuring device that can measure the position and distance of an object in a monitoring area using electromagnetic waves as a medium may be used.

  The CMOS camera 3 optically captures a monitoring area (the same as the monitoring area of the laser radar 2 or includes the monitoring area of the laser radar 2) set in front of the host vehicle 1 and outputs an image signal thereof. The CMOS camera 3 has a performance that satisfies at least the required dynamic range (100 dB or more) in outdoor photography, and can selectively read an image in an arbitrary area (random access). To do. Note that “selective readout of an image in an arbitrary area” is to select only an image in the address range by designating an arbitrary address range (row address and column address) of the effective pixel for the CMOS camera. Means to take it out.

  FIG. 1B is a conceptual diagram of random access in a CMOS camera. For example, in this case, for example, a CMOS camera in which the number of effective pixels is 640 (column) × 480 (row) pixels is taken as an example. In this case, for example, a range of 160 to 320 of row addresses and 160 to 480 of column addresses are used. If the range is designated as a read address, only the image (hatched portion) of the substantially central portion of the entire screen (640 × 480) can be extracted. Such random access (selective readout of an image in an arbitrary area) is one of the features of a CMOS camera. In other words, it is applied to a CCD camera that sequentially transfers charges accumulated in a charge coupled device such as a photodiode. There are no excellent features.

  FIG. 2 is a diagram illustrating an imaging range of the CMOS camera 3. The CMOS camera 3 images the monitoring area in front of the host vehicle 1 at an arbitrary size within the maximum shootable range (maximum random access) of a predetermined vertical field angle φa and a predetermined horizontal field angle φb. The image signal is output as a moving image of several tens of frames per second. The vertical angle of view φa and the horizontal angle of view φb are set to appropriate values capable of photographing at least the vehicle 5 (object) traveling in front of the host vehicle 1 and the white line 6 on the road surface. These values (φa and φb) may be fixed values or may be variable values that change according to the vehicle speed or the like.

  3 and 4 are diagrams showing a scan (scanning) range of the laser radar 2. FIG. 3 shows a case where the preceding vehicle 5 is detected, and FIG. 4 shows a case where the road surface (white line 6) is detected. When the preceding vehicle 5 is detected, the elevation angle (tilt angle) center of the laser beam 2a is approximately horizontal, and the upper, lower, left and right are scanned two-dimensionally. When detecting the road surface, one-dimensional scanning is performed in the horizontal direction with the elevation angle center of the laser beam 2a as a depression angle (minus angle) (or two-dimensional scanning may be performed by narrowing only the vertical width).

  The image processing unit 4 processes the image signal output from the CMOS camera 3 in accordance with a predetermined algorithm. The details of the algorithm will be described later, but generally, the scan control of the laser radar 2 and the CMOS camera 3 are performed. Random access control is performed as appropriate, and unnecessary lightness information is removed from the image signal in the random access range to reduce the amount of information (an “advance vehicle recognition image” and “white line recognition” described later). Image ") is generated, and an image signal with a reduced amount of information is output to the preceding vehicle tracking system, thereby improving the operating speed of the system (improving real-time performance).

  FIG. 5 is a conceptual configuration diagram of the image processing unit 4. In this figure, the image processing unit 4 is not particularly limited, but has a configuration of a microprogram control system including a CPU 4a, a ROM 4b, a RAM 4c, an input / output unit 4d, and the like. The image processing unit 4 having such a configuration loads software resources such as a control program written in the ROM 4b in advance into the RAM 4c and executes them on the CPU 4a, thereby executing the software resources and hardware resources such as the CPU 4a. The desired function is realized by organic bonding with the.

  6 and 7 are diagrams illustrating schematic flowcharts of software resources executed by the image processing unit 4. In this flowchart, first, two scan controls of the laser radar 2 are executed (step S11). The first scan control (step S11a) is for detecting an object in front of the host vehicle 1 (a vehicle of a preceding vehicle or other objects) (see FIG. 3). Detection information (distance etc.) of an object such as a vehicle existing in is acquired. The second scan control (step S11b) is for detecting the road surface (see FIG. 4), and the detection information (distance, etc.) of the road surface closest to the front of the host vehicle 1 is acquired by this control.

Next, image information of the CMOS camera 3 (image information of the entire screen at this stage) is acquired (step S12).
FIG. 8 is a diagram showing image information of the CMOS camera 3. FIG. 4A is an original image, and FIG. 4B is a simplified version of the original image. In these drawings, an image 7 is image information of the entire screen of the CMOS camera 3 (image information composed of all effective pixels of the CMOS camera 3). In this image 7, various subjects, for example, a traveling lane 10 (road surface) of the vehicle 1 divided by white lines 8 and 9, an adjacent lane 11 on the right side thereof, a traveling lane 10 and a vehicle 12 traveling in the adjacent lane 11. , 13 etc. are imprinted. Of the vehicles 12 and 13, the vehicle 12 traveling in the same travel lane 10 as the host vehicle 1 is referred to as a “preceding vehicle” in which attention must be paid to the movement.

  FIG. 9A is a diagram showing detection information of the laser radar 2. In this figure, a plurality of black circles (P11 to P13) superimposed and displayed on the image 7 represent detection information of the laser radar 2 for convenience. For example, P11 and P12 represent detection information of the preceding vehicle 12 detected by the first scan control (see FIG. 3), and P13 is detected by the second scan control (see FIG. 4). Road surface information (including white line information).

  In this figure, the detection information (P11 to P13) is superimposed and displayed on the image 7, but since the coordinates of the laser radar 2 and the CMOS camera 3 are not actually the same, the laser radar 2 In order to take correspondence between the detected information (P11 to P13) and the image information of the CMOS camera 3, it is necessary to convert the other coordinate on the basis of one of the coordinates (step S13). The superimposed display of the detection information (P11 to P13) shown in FIG. 9A is after the coordinate conversion.

  After executing the coordinate transformation in this way, next, the image 7 is cut out based on the detection information (P11 to P13) (step S14 and step S15). Here, “cutting out” means cutting out a specific portion of the image 7. This extraction may be performed by random access of the CMOS camera 3 or the image 7 may be performed by selective reading of a desired address range of the RAM 4c since the image 7 is expanded in the RAM 4c.

  FIG. 9B is a conceptual diagram of cutting out the image 7 in steps S14 and S15. In this figure, rectangles E11 and E12 drawn in the image 7 are cutout ranges generated around the detection information (P11 to P13) of the laser radar 2, respectively. The enclosed portion is cut out by random access from the CMOS camera 3 or by selective reading from the image 7 developed in the RAM 4c. Here, the rectangle E11 corresponds to the detection information P11 and P12 of the preceding vehicle 12, and the rectangle E12 corresponds to the road surface detection information P13. Hereinafter, an image cut out using the rectangle E11 is referred to as “object image 7a”, and an image cut out using the rectangle E12 is referred to as “road surface image 7b”.

  When the object image 7a and the road surface image 7b are cut out in this way, next, the minimum brightness value and the maximum brightness value of the object image 7a and the road surface image 7b are detected (step S16 and step S17: first and second). Second brightness value detection step). Here, the lowest brightness value has the darkest value among the brightness information of each pixel in the image, and the highest brightness value means the brightest value among the brightness information of each pixel in the image. It is what you have. Hereinafter, the minimum brightness value of the object image 7a is expressed as Ga_Bmin, the maximum brightness value is expressed as Ga_Bmax, the minimum brightness value of the road surface image 7b is expressed as Gb_Bmin, and the maximum brightness value is expressed as Gb_Bmax.

  As described above, when the minimum brightness values (Ga_Bmin, Gb_Bmin) and the maximum brightness values (Ga_Bmax, Gb_Bmax) of the object image 7a and the road surface image 7b are detected, next, an “advance vehicle recognition image in which unnecessary brightness information is reduced. ”And“ white line recognition image ”are generated, and these images are output to the preceding vehicle tracking system (step S18 and step S19: preceding vehicle recognition image generation step and white line recognition image generation step), and the flowchart ends. To do.

  Here, “unnecessary brightness information” refers to brightness information of Ga_Bmin or less and Ga_Bmax or more in the object image 7a, and in the road surface image 7b, Gb_Bmin or less and Gb_Bmax or more. It means brightness information. Such brightness information is information unnecessary for the recognition of the preceding vehicle and the recognition of the white line, and is information that causes unnecessary image processing in the preceding vehicle following system.

  Therefore, according to the present embodiment, the preceding vehicle following system can be provided with an image (an image for recognizing the preceding vehicle and an image for recognizing the white line) configured only with information necessary for the recognition of the preceding vehicle and the recognition of the white line. Thus, the operating speed of the system can be improved, and the quick response (real time performance) can be improved.

  FIG. 10 is a reference diagram showing an image 14 of the CMOS camera 3 when the brightness information is not deleted. (A) shows the image 14, (b) shows a three-dimensional map of the brightness information of the image 14, and (c) shows a histogram of the brightness information of the image 14. The “mountain” of the three-dimensional map is a portion with high brightness (bright), and the “valley” is a portion with low brightness (dark). The histogram waveform represents the appearance frequency of each brightness value, and the length of the horizontal axis of the histogram corresponds to the dynamic range of the CMOS camera 3. When the brightness information is not deleted, the preceding vehicle following system must process all of the large amount of information included in the illustrated image 14, and the processing load on the system is considerable.

  On the other hand, FIG.11 and FIG.12 is a figure which shows the images 15 and 16 of the CMOS camera 3 at the time of deleting the said brightness information. An image 15 shown in FIG. 11 is obtained by deleting brightness information below Ga_Bmin and Ga_Bmax, and an image 16 shown in FIG. 12 is obtained by deleting brightness information below Gb_Bmin and above Gb_Bmax. That is, the image 15 corresponds to the “preceding vehicle recognition image” in step S18, and the image 16 corresponds to the “white line recognition image” in step S19.

  Looking at the histograms of these two images 15 and 16 (the preceding vehicle recognition image and the white line recognition image), the former image 15 (the preceding vehicle recognition image) shows brightness information in a specific range from Ga_Bmin to Ga_Bmax. Contains only. Similarly, the latter image 16 (white line recognition image) also includes only brightness information in a specific range from Gb_Bmin to Gb_Bmax.

  That is, the former image 15 (preceding vehicle recognition image) is an image obtained by discarding brightness information of Ga_Bmin or less and Ga_Bmax or more of the original image (image 14 in FIG. 10), and the latter image 16 (white line recognition). Image) is also an image obtained by discarding the brightness information of Gb_Bmin or less and Gb_Bmax or more of the original image (image 14 in FIG. 10). Therefore, these two images 15 and 16 (preceding vehicle recognition image and white line recognition image) The amount of information of the image is clearly less than that of the original image (image 14 in FIG. 10).

  Therefore, according to the present embodiment, the processing load of the preceding vehicle tracking system that processes these two images 15 and 16 (the preceding vehicle recognition image and the white line recognition image) can be greatly reduced. It is possible to improve the operation speed and improve the responsiveness (real-time property).

  Further, examples of the preceding vehicle recognition image and the white line recognition image (images 15 and 16 of the CMOS camera 3 when the brightness information is deleted) shown in FIG. 11 and FIG. However, the present invention is not limited to this, and the CMOS camera 3 may be randomly accessed to selectively acquire images in a desired range, and these selected images may be used as a preceding vehicle recognition image and a white line recognition image, respectively. The random access range in this case can be specified using, for example, the rectangles E11 and E12 in FIG. 9B.

  If random access is also used in this way, the number of pixels can be reduced by reducing the image size of the preceding vehicle recognition image and the white line recognition image to the minimum necessary size, coupled with the deletion of the brightness information, Further, it is preferable because the responsiveness (real-time property) of the preceding vehicle following system can be improved.

1 is a system configuration diagram of an embodiment and a conceptual diagram of random access in a CMOS camera. 2 is a diagram illustrating an imaging range of a CMOS camera 3. FIG. It is a figure which shows the scanning range (when detecting the preceding vehicle 5) of the laser radar 2. FIG. It is a figure which shows the scanning range (thing when detecting a road surface) of the laser radar. 2 is a conceptual configuration diagram of an image processing unit 4. FIG. It is a figure (1/2) which shows the schematic flowchart of the software resource performed with the image process part. FIG. 3B is a diagram (2/2) illustrating a schematic flowchart of software resources executed by the image processing unit 4; It is a figure which shows the image information of the CMOS camera. It is the figure which shows the detection information of the laser radar 2, and the conceptual diagram of extraction of the image 7 in step S14 and step S15. It is a figure which shows the image 14 of the CMOS camera 3 when not deleting brightness information. It is a figure which shows the image 15 (image for a preceding vehicle recognition) of the CMOS camera 3 at the time of deleting brightness information. It is a figure which shows the image 16 (image for white line recognition) of the CMOS camera 3 at the time of deleting brightness information.

Explanation of symbols

Ga_Bmin minimum brightness value Ga_Bmax maximum brightness value Gb_Bmin minimum brightness value Gb_Bmax maximum brightness value S16 step (first brightness value detection process)
S17 step (second brightness value detection step)
S18 step (image generation process for preceding vehicle recognition)
S19 Step (Image generation process for white line recognition)
1 Vehicle 2 Laser radar (radar)
3 CMOS camera (imaging device)
4 Image processing unit (first brightness value detection means, second brightness value detection means, preceding vehicle recognition image generation means, white line recognition image generation means)
5 Vehicle (object)
7 image 7a object image 7b road surface image 10 traveling lane (road surface)
14 image 15 preceding vehicle recognition image 16 white line recognition image

Claims (4)

Based on the detection information from the radar that detects the object in front of the host vehicle and the road surface in front of the host vehicle, the preceding vehicle recognition image and the road surface in front of the host vehicle among the images in front of the host vehicle captured by the imaging device In the image processing apparatus that extracts the white line recognition image above,
According to the detection information of the object ahead of the host vehicle detected by the radar, an object image including the object is extracted from the image ahead of the host vehicle, and a minimum brightness value and a maximum brightness value of the object image are detected. A lightness value detection means;
In accordance with the detection information of the road surface immediately in front of the host vehicle detected by the radar, a road surface image including the road surface is extracted from the image ahead of the host vehicle, and the minimum brightness value and the maximum brightness value of the road image are detected. A second brightness value detecting means;
Preceding vehicle recognition image generation means for generating, as the preceding vehicle recognition image, information obtained by discarding information below the minimum brightness value and the maximum brightness value of the object image among the brightness information of the image ahead of the host vehicle;
White line recognition image generating means for generating, as the white line recognition image, information obtained by discarding information below the minimum brightness value and the maximum brightness value of the road surface image among the brightness information of the image ahead of the vehicle. An image processing apparatus. Based on the detection information from the radar that detects the object in front of the host vehicle and the road surface in front of the host vehicle, the preceding vehicle recognition image in front of the host vehicle and the road surface from among the images in front of the host vehicle captured by the imaging device In the image processing method for extracting the white line recognition image above,
According to the detection information of the object ahead of the host vehicle detected by the radar, an object image including the object is extracted from the image ahead of the host vehicle, and a minimum brightness value and a maximum brightness value of the object image are detected. A brightness value detection process;
In accordance with the detection information of the road surface immediately in front of the host vehicle detected by the radar, a road surface image including the road surface is extracted from the image ahead of the host vehicle, and the minimum brightness value and the maximum brightness value of the road image are detected. A second brightness value detection step;
A preceding vehicle recognition image generating step for generating, as the preceding vehicle recognition image, information obtained by discarding information below the minimum brightness value and the maximum brightness value of the object image among the brightness information of the image ahead of the host vehicle;
A white line recognition image generating step for generating, as the white line recognition image, information obtained by discarding information below the minimum brightness value and the maximum brightness value of the road surface image among the brightness information of the image ahead of the vehicle. An image processing method characterized by the above. The image processing apparatus according to claim 1, wherein the imaging device is a CMOS camera. The image processing method according to claim 3, wherein the imaging device is a CMOS camera.

Images